© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 234310
    Prev
    Next
    INDEX
    Explanations

    phrases following "We", "down", "table", "hundreds", "any", "perhaps", "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LA
    0.49
    AIRE
    0.49
    ២
    0.47
     學
    0.47
    UEST
    0.46
    GORITH
    0.45
     พิจิก
    0.45
    tudo
    0.44
    }^{*}
    0.44
     আয়নগুলির
    0.44
    POSITIVE LOGITS
    ة
    0.56
    processors
    0.46
    ヌ
    0.45
    ەوە
    0.44
    陨
    0.44
     sunken
    0.43
     هنا
    0.43
     hồn
    0.43
    ución
    0.42
    olytic
    0.42
    Activations Density 0.000%

    No Known Activations